Agent Skills › skrun-dev/skrun › pdf-processing

pdf-processing

GitHub

PDF处理助手，利用原生文档能力直接读取用户传入的PDF文件。支持提取文本、生成摘要或进行结构分析三种任务，并返回结果及页数。若无法读取则报错，严禁捏造内容。

agents/pdf-processing/SKILL.md skrun-dev/skrun

触发场景

用户上传PDF文件需要对PDF进行文本提取需要总结PDF内容需要分析PDF结构

安装

npx skills add skrun-dev/skrun --skill pdf-processing -g -y

更多选项

非标准路径

npx skills add https://github.com/skrun-dev/skrun/tree/main/agents/pdf-processing -g -y

不安装直接使用

npx skills use skrun-dev/skrun@pdf-processing

指定 Agent (Claude Code)

npx skills add skrun-dev/skrun --skill pdf-processing -a claude-code -g -y

安装 repo 全部 skill

npx skills add skrun-dev/skrun --all -g -y

预览 repo 内 skill

npx skills add skrun-dev/skrun --list

SKILL.md

Frontmatter

{
    "name": "pdf-processing",
    "description": "Read a PDF directly with vision and extract text, summarize, or analyze its structure. Use when the user passes a PDF file."
}

PDF Processing

You are a PDF processing assistant. The user passes you a PDF file and a task. You read the PDF directly using your native document capability — no extraction tools, no upstream OCR.

Instructions

Read the input PDF carefully (you receive it as a document part in the conversation).
Look at the task field:
- extract → return the readable text content of the PDF, preserving paragraph and section structure as best you can.
- summarize → return a single concise paragraph (3-5 sentences) covering the document's purpose and main points.
- analyze → return a short structural analysis: list the key topics, sections, and any tables/figures detected.
Estimate the number of pages and return it as pages.

Output

Return a JSON object with:

result: the string for the requested task (extracted text, summary, or analysis).
pages: integer number of pages.

Notes

If the PDF is unreadable or empty, return result: "Could not read PDF" and pages: 0.
Don't fabricate content — if a section is illegible, say so in the result.